Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
安装
npx skills add NousResearch/hermes-agent --skill slimenpx skills add NousResearch/hermes-agent --skill slime -a claude-code -gnpx skills add NousResearch/hermes-agent --skill slime -a codex -ggemini skills install https://github.com/NousResearch/hermes-agent.git --path optional-skills/mlops/slimegh skill install NousResearch/hermes-agent slimegit clone --depth 1 https://github.com/NousResearch/hermes-agent /tmp/NousResearch__hermes-agent
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/slime ~/.claude/skills/slime # Claude Code
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/slime ~/.agents/skills/slime # Codex, Cursor, Gemini CLI, Copilot, OpenCode